Landscape Ecology

, Volume 28, Issue 10, pp 1989–2004 | Cite as

Predicting fire occurrence patterns with logistic regression in Heilongjiang Province, China

  • Yu ChangEmail author
  • Zhiliang Zhu
  • Rencang Bu
  • Hongwei Chen
  • Yuting Feng
  • Yuehui Li
  • Yuanman Hu
  • Zhicheng Wang
Research article


Prediction of forest fire ignition may aid in forest fire vigilance and monitoring, and in prioritizing forest fuel treatments. In this paper, we chose easily obtained spatial variables pertaining to topography, vegetation types, meteorological conditions, climate, and human activity to predict forest fire ignition in Heilongjiang province, China, using logistic regression. Results showed fire ignition prediction through logistic regression had good accuracy. Climatic variables (e.g., average annual mean temperature and precipitation) and meteorological conditions (e.g., daily minimum temperature, daily minimum humidity, daily mean humidity, and mean wind speed) are the main determinants of natural forest fires. In the case of anthropogenic fires, vegetation types and human activity as indicated by distances to roads and settlements combined with suitable meteorological conditions (e.g., daily mean humidity) are the main driving factors. The fire ignition probability map can be easily used to prioritize areas for vigilance, to make decisions on allocating firefighting resources, and to select vulnerable spots for forest fuel treatments. It was found that forest fuel treatments should be focused on the Great Xing’an Mountains.


Logistic regression Forest fire Fire occurrence Receiver operating characteristic curve Heilongjiang province China 



This research was supported by The National Natural Science Foundation of China (Grant No. 31070422, 41201185, 41271201), and the Strategic Priority Research Program-Climate Change: Carbon Budget and Related Issues of the Chinese Academy of Sciences (Grant No. XDA05050201). We thank the Chinese Forestry Science Data Center ( for providing fire record data, and the China Meteorological Data sharing Service System ( for providing observational meteorological data. DEM data were provided by the International Scientific & Technical Data Mirror Site, Computer Network Information Center, Chinese Academy of Sciences ( We thank the anonymous reviewers for helpful suggestions that improved the manuscript.


  1. Avila-Flores D, Pompa-Garcia M, Antonio-Nemiga X, Rodriguez-Trejo D, Vargas-Perez E, Santillan-Perez J (2010) Driving factors for forest fire occurrence in Durango State of Mexico: a geospatial perspective. Chin Geo Sci 20:491–497CrossRefGoogle Scholar
  2. Carmo M, Moreira F, Casimiro P, Vaz P (2011) Land use and topography influences on wildfire occurrence in northern Portugal. Landsc Urban Plan 100:169–176CrossRefGoogle Scholar
  3. Catry FX, Rego FC, Bação FL, Moreira F (2009) Modeling and mapping wildfire ignition risk in Portugal. Int J Wildland Fire 18:921–931CrossRefGoogle Scholar
  4. Chang Y, He HS, Bishop I, Hu Y, Bu R, Xu C, Li X (2007) Long-term forest landscape responses to fire exclusion in the Great Xing’an Mountains, China. Int J Wildland Fire 16:34–44CrossRefGoogle Scholar
  5. Chang Y, He HS, Hu Y, Bu R, Li X (2008) Historic and current fire regimes in the Great Xing’an Mountains, northeastern China: implications for long-term forest management. For Ecol Manag 254:445–453CrossRefGoogle Scholar
  6. Chuvieco E, González I, Verdú F, Aguado I, Yebra M (2009) Prediction of fire occurrence from live fuel moisture content measurements in a Mediterranean ecosystem. Int J Wildland Fire 18:430–441CrossRefGoogle Scholar
  7. de la Riva J, Perez-Cabello F, Lana-Renault N, Koutsias N (2004) Mapping wildfire occurrence at regional scale. Remote Sens Environ 92:363–369CrossRefGoogle Scholar
  8. de Vasconcelos MJP, Silva S, Tome M, Alvim M, Pereira J (2001) Spatial prediction of fire ignition probabilities: comparing logistic regression and neural networks. Photogramm Eng Remote Sens 67:73–81Google Scholar
  9. del Hoyo VL, Martín Isabel M, Martínez Vega F (2011) Logistic regression models for human-caused wildfire risk estimation: analysing the effect of the spatial accuracy in fire occurrence data. Eur J For Res 130:983–996CrossRefGoogle Scholar
  10. Deng XW, Wen DY, Deng SW (2003) A preliminary study of the relationship between forest fire and landscape pattern. Fire Saf Sci 12:238–244 (in Chinese)Google Scholar
  11. Di LY, Sun RY (2007) Summarization of research on forest fire in China. J Catastrophol 4:118–123 (in Chinese)Google Scholar
  12. Díaz-Delgado R, Lloret F, Pons X (2004) Spatial patterns of fire occurrence in Catalonia, NE, Spain. Landsc Ecol 19:731–745CrossRefGoogle Scholar
  13. Dickson BG, Prather JW, Xu Y, Hampton HM, Aumack EN, Sisk TD (2006) Mapping the probability of large fire occurrence in northern Arizona, USA. Landsc Ecol 21:747–762CrossRefGoogle Scholar
  14. Dlamini WM (2010) A Bayesian belief network analysis of factors influencing wildfire occurrence in Swaziland. Environ Model Soft 25:199–208CrossRefGoogle Scholar
  15. Fielding AH, Bell JF (1997) A review of methods for the assessment of prediction errors in conservation presence/absence models. Environ Conserv 24:38–49CrossRefGoogle Scholar
  16. Finney MA (2007) A computational method for optimising fuel treatment locations. Int J Wildland Fire 16:702–711CrossRefGoogle Scholar
  17. Garcia CV, Woodard P, Titus S, Adamowicz W, Lee B (1995) A logit model for predicting the daily occurrence of human caused forest-fires. Int J Wildland Fire 5:101–111CrossRefGoogle Scholar
  18. Hein S, Weiskittel A (2010) Cutpoint analysis for models with binary outcomes: a case study on branch mortality. Eur J For Res 129:585–590CrossRefGoogle Scholar
  19. Hering AS, Bell CL, Genton MG (2009) Modeling spatio-temporal wildfire ignition point patterns. Environ Ecol Stat 16:225–250CrossRefGoogle Scholar
  20. Hosmer DW, Lemeshow S (2000) Applied logistic regression. Wiley, New YorkCrossRefGoogle Scholar
  21. Hosmer DW, Hosmer T, Le Cessie S, Lemeshow S (1997) A comparison of goodness-of-fit tests for the logistic regression model. Stat Med 16:965–980PubMedCrossRefGoogle Scholar
  22. Hu H, Jin S (2002) Study on forest fire regime of Heilongjiang province II. Analysis on factors affecting fire dynamics and distributions. Scientia Silvae Sinicae 38:98–102 (in Chinese)Google Scholar
  23. Jiménez-Valverde A (2012) Insights into the area under the receiver operating characteristic curve (AUC) as a discrimination measure in species distribution modelling. Glob Ecol Biogeogr 21:498–507CrossRefGoogle Scholar
  24. Koutsias N, Kalabokidis KD, Allg wer B (2004) Fire occurrence patterns at landscape level: beyond positional accuracy of ignition points with kernel density estimation methods. Nat Resour Model 17:359–375CrossRefGoogle Scholar
  25. Legendre P, Legendre L (1998) Numerical ecology. Elsevier, AmsterdamGoogle Scholar
  26. Liu Z, Yang J, Chang Y, Weisberg PJ, He HS (2012) Spatial patterns and drivers of fire occurrence and its future trend under climate change in a boreal forest of Northeast China. Glob Change Biol 18:2041–2056CrossRefGoogle Scholar
  27. Lozano FJ, Suárez-Seoane S, de Luis E (2007) Assessment of several spectral indices derived from multi-temporal landsat data for fire occurrence probability modelling. Remote Sens Environ 107:533–544CrossRefGoogle Scholar
  28. Lozano FJ, Suarez-Seoane S, Kelly M, Luis E (2008) A multi-scale approach for modeling fire occurrence probability using satellite data and classification trees: a case study in a mountainous Mediterranean region. Remote Sens Environ 112:708–719CrossRefGoogle Scholar
  29. Maingi JK, Henry MC (2007) Factors influencing wildfire occurrence and distribution in eastern Kentucky, USA. Int J Wildland Fire 16:23–33CrossRefGoogle Scholar
  30. Martell DL, Otukol S, Stocks BJ (1987) A logistic model for predicting daily people-caused forest fire occurrence in Ontario. Can J For Res 17:394–401CrossRefGoogle Scholar
  31. Oliveira S, Oehler F, San-Miguel-Ayanz J, Camia A, Pereira JMC (2012) Modeling spatial patterns of fire occurrence in Mediterranean Europe using Multiple Regression and Random Forest. For Ecol Manag 275:117–129CrossRefGoogle Scholar
  32. Padilla M, Vega-García C (2011) On the comparative importance of fire danger rating indices and their integration with spatial and temporal variables for predicting daily human-caused fire occurrences in Spain. Int J Wildland Fire 20:46–58CrossRefGoogle Scholar
  33. Phillips SJ, Elith J (2010) POC plots: calibrating species distribution models with presence-only data. Ecology 91:2476–2484PubMedCrossRefGoogle Scholar
  34. Podur J, Martell DL, Csillag F (2003) Spatial patterns of lightning-caused forest fires in Ontario, 1976–1998. Ecol Model 164:1–20CrossRefGoogle Scholar
  35. Preisler HK, Westerling AL, Gebert KM, Munoz-Arriola F, Holmes TP (2011) Spatially explicit forecasts of large wildland fire probability and suppression costs for California. Int J Wildland Fire 20:508–517CrossRefGoogle Scholar
  36. Puri K, Areendran G, Raj K, Mazumdar S, Joshi P (2011) Forest fire risk assessment in parts of Northeast India using geospatial tools. J For Res 22:641–647CrossRefGoogle Scholar
  37. Sağlam B, Bilgili E, Durmaz BD, Kadıoğulları Aİ, Küçük Ö (2008) Spatio-temporal analysis of forest fire risk and danger using landsat imagery. Sensors 8:3970–3987CrossRefGoogle Scholar
  38. Shu L, Tian X (1999) The research and application of the sustainable management technique of Forest Fuel. Fire Saf Sci 8:18–24 (in Chinese)Google Scholar
  39. Swets JA (1988) Measuring the accuracy of diagnostic systems. Science 240:1285–1293PubMedCrossRefGoogle Scholar
  40. Vilar L, Woolford DG, Martell DL, Martín MP (2010) A model for predicting human-caused wildfire occurrence in the region of Madrid, Spain. Int J Wildland Fire 19:325–337CrossRefGoogle Scholar
  41. Wei Y, Rideout D, Kirsch A (2008) An optimization model for locating fuel treatments across a landscape to reduce expected fire losses. Can J For Res 38:868–877CrossRefGoogle Scholar
  42. Xu H (1998) Da Hinggan Ling Mountains forests in China. In. Scientific Press, Beijing (in Chinese)Google Scholar
  43. Yang J, He HS, Shifley SR, Gustafson EJ (2007) Spatial patterns of modern period human-caused fire occurrence in the Missouri Ozark Highlands. For Sci 53:1–15Google Scholar
  44. Zhao FJ, Shu LF (2007) The effects of abnormal climate on forest fire occurrence. For Fire Prevent 1:21–23 (in Chinese)Google Scholar
  45. Zhou Y (1991) Vegetation of Greater Xingan in China. Scientific Press, Beijing (in Chinese)Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  • Yu Chang
    • 1
    Email author
  • Zhiliang Zhu
    • 2
  • Rencang Bu
    • 1
  • Hongwei Chen
    • 1
  • Yuting Feng
    • 1
  • Yuehui Li
    • 1
  • Yuanman Hu
    • 1
  • Zhicheng Wang
    • 3
  1. 1.State Key Laboratory of Forest and Soil Ecology, Institute of Applied EcologyChinese Academy of SciencesShenyangChina
  2. 2.U.S. Geological SurveyRestonUSA
  3. 3.Heilongjiang Forest Fire Prevention OfficeHarbinChina

Personalised recommendations